aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/spinlock.h
blob: ee67edf86fdd98929998276ad8e5ab02c93c333a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
#ifndef _ASM_X86_SPINLOCK_H
#define _ASM_X86_SPINLOCK_H

#include <linux/atomic.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
#include <asm/paravirt.h>
/*
 * Your basic SMP spinlocks, allowing only a single CPU anywhere
 *
 * Simple spin lock operations.  There are two variants, one clears IRQ's
 * on the local processor, one does not.
 *
 * These are fair FIFO ticket locks, which are currently limited to 256
 * CPUs.
 *
 * (the type definitions are in asm/spinlock_types.h)
 */

#ifdef CONFIG_X86_32
# define LOCK_PTR_REG "a"
# define REG_PTR_MODE "k"
#else
# define LOCK_PTR_REG "D"
# define REG_PTR_MODE "q"
#endif

#if defined(CONFIG_X86_32) && \
	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
/*
 * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
 * (PPro errata 66, 92)
 */
# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
#else
# define UNLOCK_LOCK_PREFIX
#endif

/*
 * Ticket locks are conceptually two parts, one indicating the current head of
 * the queue, and the other indicating the current tail. The lock is acquired
 * by atomically noting the tail and incrementing it by one (thus adding
 * ourself to the queue and noting our position), then waiting until the head
 * becomes equal to the the initial value of the tail.
 *
 * We use an xadd covering *both* parts of the lock, to increment the tail and
 * also load the position of the head, which takes care of memory ordering
 * issues and should be optimal for the uncontended case. Note the tail must be
 * in the high part, because a wide xadd increment of the low part would carry
 * up and contaminate the high part.
 *
 * With fewer than 2^8 possible CPUs, we can use x86's partial registers to
 * save some instructions and make the code more elegant. There really isn't
 * much between them in performance though, especially as locks are out of line.
 */
#if (NR_CPUS < 256)
#define TICKET_SHIFT 8

static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
{
	short inc = 0x0100;

	asm volatile (
		LOCK_PREFIX "xaddw %w0, %1\n"
		"1:\t"
		"cmpb %h0, %b0\n\t"
		"je 2f\n\t"
		"rep ; nop\n\t"
		"movb %1, %b0\n\t"
		/* don't need lfence here, because loads are in-order */
		"jmp 1b\n"
		"2:"
		: "+Q" (inc), "+m" (lock->slock)
		:
		: "memory", "cc");
}

static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
{
	int tmp, new;

	asm volatile("movzwl %2, %0\n\t"
		     "cmpb %h0,%b0\n\t"
		     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
		     "jne 1f\n\t"
		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
		     "1:"
		     "sete %b1\n\t"
		     "movzbl %b1,%0\n\t"
		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
		     :
		     : "memory", "cc");

	return tmp;
}

static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
{
	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
		     : "+m" (lock->slock)
		     :
		     : "memory", "cc");
}
#else
#define TICKET_SHIFT 16

static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
{
	int inc = 0x00010000;
	int tmp;

	asm volatile(LOCK_PREFIX "xaddl %0, %1\n"
		     "movzwl %w0, %2\n\t"
		     "shrl $16, %0\n\t"
		     "1:\t"
		     "cmpl %0, %2\n\t"
		     "je 2f\n\t"
		     "rep ; nop\n\t"
		     "movzwl %1, %2\n\t"
		     /* don't need lfence here, because loads are in-order */
		     "jmp 1b\n"
		     "2:"
		     : "+r" (inc), "+m" (lock->slock), "=&r" (tmp)
		     :
		     : "memory", "cc");
}

static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
{
	int tmp;
	int new;

	asm volatile("movl %2,%0\n\t"
		     "movl %0,%1\n\t"
		     "roll $16, %0\n\t"
		     "cmpl %0,%1\n\t"
		     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
		     "jne 1f\n\t"
		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
		     "1:"
		     "sete %b1\n\t"
		     "movzbl %b1,%0\n\t"
		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
		     :
		     : "memory", "cc");

	return tmp;
}

static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
{
	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
		     : "+m" (lock->slock)
		     :
		     : "memory", "cc");
}
#endif

static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
{
	int tmp = ACCESS_ONCE(lock->slock);

	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
}

static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
{
	int tmp = ACCESS_ONCE(lock->slock);

	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
}

#ifndef CONFIG_PARAVIRT_SPINLOCKS

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	return __ticket_spin_is_locked(lock);
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	return __ticket_spin_is_contended(lock);
}
#define arch_spin_is_contended	arch_spin_is_contended

static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
{
	__ticket_spin_lock(lock);
}

static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	return __ticket_spin_trylock(lock);
}

static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	__ticket_spin_unlock(lock);
}

static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
						  unsigned long flags)
{
	arch_spin_lock(lock);
}

#endif	/* CONFIG_PARAVIRT_SPINLOCKS */

static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
	while (arch_spin_is_locked(lock))
		cpu_relax();
}

/*
 * Read-write spinlocks, allowing multiple readers
 * but only one writer.
 *
 * NOTE! it is quite common to have readers in interrupts
 * but no interrupt writers. For those circumstances we
 * can "mix" irq-safe locks - any writer needs to get a
 * irq-safe write-lock, but readers can get non-irqsafe
 * read-locks.
 *
 * On x86, we implement read-write locks as a 32-bit counter
 * with the high bit (sign) being the "contended" bit.
 */

/**
 * read_can_lock - would read_trylock() succeed?
 * @lock: the rwlock in question.
 */
static inline int arch_read_can_lock(arch_rwlock_t *lock)
{
	return lock->lock > 0;
}

/**
 * write_can_lock - would write_trylock() succeed?
 * @lock: the rwlock in question.
 */
static inline int arch_write_can_lock(arch_rwlock_t *lock)
{
	return lock->write == WRITE_LOCK_CMP;
}

static inline void arch_read_lock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t"
		     "jns 1f\n"
		     "call __read_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (rw) : "memory");
}

static inline void arch_write_lock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t"
		     "jz 1f\n"
		     "call __write_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS)
		     : "memory");
}

static inline int arch_read_trylock(arch_rwlock_t *lock)
{
	READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock;

	if (READ_LOCK_ATOMIC(dec_return)(count) >= 0)
		return 1;
	READ_LOCK_ATOMIC(inc)(count);
	return 0;
}

static inline int arch_write_trylock(arch_rwlock_t *lock)
{
	atomic_t *count = (atomic_t *)&lock->write;

	if (atomic_sub_and_test(WRITE_LOCK_CMP, count))
		return 1;
	atomic_add(WRITE_LOCK_CMP, count);
	return 0;
}

static inline void arch_read_unlock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0"
		     :"+m" (rw->lock) : : "memory");
}

static inline void arch_write_unlock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0"
		     : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory");
}

#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

#undef READ_LOCK_SIZE
#undef READ_LOCK_ATOMIC
#undef WRITE_LOCK_ADD
#undef WRITE_LOCK_SUB
#undef WRITE_LOCK_CMP

#define arch_spin_relax(lock)	cpu_relax()
#define arch_read_relax(lock)	cpu_relax()
#define arch_write_relax(lock)	cpu_relax()

/* The {read|write|spin}_lock() on x86 are full memory barriers. */
static inline void smp_mb__after_lock(void) { }
#define ARCH_HAS_SMP_MB_AFTER_LOCK

#endif /* _ASM_X86_SPINLOCK_H */